© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 49828
    Prev
    Next
    INDEX
    Explanations

    female identity types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æŀĦæĪIJçĬ¯ç½ªçļĦ
    -0.08
    СÐĺ
    -0.07
    loff
    -0.07
    æĪĸ缴æİ¥
    -0.07
     themselves
    -0.07
    ç»Ŀ伦
    -0.07
    à¹Ģà¸Ķà¹ĩà¸Ķ
    -0.07
    annies
    -0.06
    ÑĢоз
    -0.06
    ä»İçİ°åľ¨å¼Ģå§ĭ
    -0.06
    POSITIVE LOGITS
    åºĶæľīçļĦ
    0.11
    该æľīçļĦ
    0.11
    å°ijæľīçļĦ
    0.10
    çļĦä¸Ģåijĺ
    0.10
    çļĦ身份
    0.09
    åºĶåħ·å¤ĩ
    0.09
    身份
    0.08
    çī¹æľīçļĦ
    0.08
    çIJĨåºĶ
    0.08
    身份çļĦ
    0.08
    Activations Density 0.371%

    No Known Activations